A collaborative machine learning-optimization algorithm to improve the finite element model updating of civil engineering structures

Finite element model updating has become a key tool to improve the numerical modelling of existing civil engineering structures, by adjusting the numerical response to the observed experimental behaviour of the structure. At present, model updating is mostly conducted using the maximum likelihood me...

ver descrição completa

Detalhes bibliográficos
Autores: Naranjo Pérez, Javier, Infantes, María, Jiménez Alonso, Javier Fernando, Sáez Pérez, Andrés
Formato: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2020
País:España
Recursos:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/180728
Acesso em linha:https://hdl.handle.net/11441/180728
https://doi.org/10.1016/j.engstruct.2020.111327
Access Level:acceso abierto
Palavra-chave:Multi-objective harmony search optimization
Machine learning
Collaborative algorithm
Best Pareto solution
Finite element model updating
Maximum likelihood method
id ES_e26a89cbde8564f53ef201d036ac1392
oai_identifier_str oai:idus.us.es:11441/180728
network_acronym_str ES
network_name_str España
spelling A collaborative machine learning-optimization algorithm to improve the finite element model updating of civil engineering structures Naranjo Pérez, Javier Infantes, María Jiménez Alonso, Javier Fernando Sáez Pérez, Andrés Multi-objective harmony search optimization Machine learning Collaborative algorithm Best Pareto solution Finite element model updating Maximum likelihood method Finite element model updating has become a key tool to improve the numerical modelling of existing civil engineering structures, by adjusting the numerical response to the observed experimental behaviour of the structure. At present, model updating is mostly conducted using the maximum likelihood method. Following this approach, the updating problem can be transformed into a multi-objective optimization problem. Due to the complex nonlinear behaviour of the resulting objective functions, metaheuristic optimization algorithms are normally employed to solve such optimization problem. However, and although this is nowadays a well-established technique, there are still two main drawbacks that need to be addressed for practical engineering applications, namely: (i) the high simulation time required to compute the problem; and (ii) the uncertainty associated with the selection of the best updated model among all the Pareto optimal solutions. In order to overcome these limitations, a new collaborative algorithm is proposed herein, which takes advantage of the collaborative coupling among two optimization algorithms (harmony search and active-set algorithms), a machine learning technique (artificial neural networks) and a statistical tool (principal component analysis). The implementation details of our proposal are discussed in detail throughout the paper and its performance is illustrated with a case study addressing the model updating of a real steel footbridge. Two are the main advantages of the newly proposed algorithm: (i) it leads to a clear reduction of the simulation time; and (ii) it further permits a robust selection of the best updated model. Elsevier https://hdl.handle.net/11441/180728 https://doi.org/10.1016/j.engstruct.2020.111327
title A collaborative machine learning-optimization algorithm to improve the finite element model updating of civil engineering structures
spellingShingle A collaborative machine learning-optimization algorithm to improve the finite element model updating of civil engineering structures
Naranjo Pérez, Javier
Multi-objective harmony search optimization
Machine learning
Collaborative algorithm
Best Pareto solution
Finite element model updating
Maximum likelihood method
title_short A collaborative machine learning-optimization algorithm to improve the finite element model updating of civil engineering structures
title_full A collaborative machine learning-optimization algorithm to improve the finite element model updating of civil engineering structures
title_fullStr A collaborative machine learning-optimization algorithm to improve the finite element model updating of civil engineering structures
title_full_unstemmed A collaborative machine learning-optimization algorithm to improve the finite element model updating of civil engineering structures
title_sort A collaborative machine learning-optimization algorithm to improve the finite element model updating of civil engineering structures
author Naranjo Pérez, Javier
author_facet Naranjo Pérez, Javier
Infantes, María
Jiménez Alonso, Javier Fernando
Sáez Pérez, Andrés
author_role author
author2 Infantes, María
Jiménez Alonso, Javier Fernando
Sáez Pérez, Andrés
author2_role author
author
author
topic Multi-objective harmony search optimization
Machine learning
Collaborative algorithm
Best Pareto solution
Finite element model updating
Maximum likelihood method
topic_facet Multi-objective harmony search optimization
Machine learning
Collaborative algorithm
Best Pareto solution
Finite element model updating
Maximum likelihood method
description Finite element model updating has become a key tool to improve the numerical modelling of existing civil engineering structures, by adjusting the numerical response to the observed experimental behaviour of the structure. At present, model updating is mostly conducted using the maximum likelihood method. Following this approach, the updating problem can be transformed into a multi-objective optimization problem. Due to the complex nonlinear behaviour of the resulting objective functions, metaheuristic optimization algorithms are normally employed to solve such optimization problem. However, and although this is nowadays a well-established technique, there are still two main drawbacks that need to be addressed for practical engineering applications, namely: (i) the high simulation time required to compute the problem; and (ii) the uncertainty associated with the selection of the best updated model among all the Pareto optimal solutions. In order to overcome these limitations, a new collaborative algorithm is proposed herein, which takes advantage of the collaborative coupling among two optimization algorithms (harmony search and active-set algorithms), a machine learning technique (artificial neural networks) and a statistical tool (principal component analysis). The implementation details of our proposal are discussed in detail throughout the paper and its performance is illustrated with a case study addressing the model updating of a real steel footbridge. Two are the main advantages of the newly proposed algorithm: (i) it leads to a clear reduction of the simulation time; and (ii) it further permits a robust selection of the best updated model.
publishDate 2020
format article
status_str acceptedVersion
url https://hdl.handle.net/11441/180728
https://doi.org/10.1016/j.engstruct.2020.111327
eu_rights_str_mv openAccess
publisher Elsevier
institution Universidad de Sevilla (US)
collection idUS. Depósito de Investigación de la Universidad de Sevilla
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
instname_str Universidad de Sevilla (US)
_version_ 1878441998836301824
publishDateSort 2020
author_browse Infantes, María
Jiménez Alonso, Javier Fernando
Naranjo Pérez, Javier
Sáez Pérez, Andrés
publisherStr Elsevier
score 6,9303427

Registos relacionados